Skip to content
cccskills
FreePublished on GitHub

add-rtk

Install rtk in NanoClaw agent containers to compress development command output and reduce token use. A Claude Code hook automatically routes Bash calls through rtk, with runtime checks to verify installation and a command to inspect savings.

OriginalShow the original description

Install rtk token-compression proxy into agent containers. Routes Bash tool calls through rtk for 60–90% token savings on dev commands (git, cargo, pytest, docker, kubectl, etc.).

Works withKubernetes
See how to install

Good for

  • Reduce token use from development command output
  • Automatically route Bash calls through rtk
  • Configure rtk for multiple agent groups
  • Check installation problems and token savings

Files included (2)

  • SKILL.md4.4 KB
  • REMOVE.md1.2 KB

SKILL.md (original)

Review the instructions the agent will receive before you install.

Add rtk

Install rtk — a CLI proxy delivering 60–90% token savings on common dev commands (git, cargo, pytest, docker, kubectl, etc.) — and wire it transparently into agent containers via the Claude Code PreToolUse hook.

What this sets up

  • rtk binary at ~/.local/bin/rtk on the host
  • ~/.local/bin/rtk mounted read-only at /usr/local/bin/rtk inside the target agent group's containers
  • PreToolUse hook in the agent group's settings.json so every Bash call is automatically filtered through rtk — no CLAUDE.md instructions needed

Integration tests

This skill has no in-tree integration test by design. Its only functional reach-ins are runtime operator actions — the host-only ncl groups config add-mount (Step 3) and the settings.json PreToolUse hook write (Step 4) — neither of which leaves a line in the source tree whose deletion a test could catch. There are no package dependencies or Dockerfile edits to guard either. Conformance is idempotent apply + REMOVE.md; the mount and hook are verified at runtime (see Verify).

Step 1 — Install rtk on the host

curl -fsSL https://raw.githubusercontent.com/rtk-ai/rtk/refs/heads/master/install.sh | sh

If the script put the binary elsewhere, move it:

find ~/.local ~/.cargo/bin ~/bin -name rtk 2>/dev/null
mv "$(which rtk 2>/dev/null)" ~/.local/bin/rtk

Verify:

~/.local/bin/rtk --version
chmod +x ~/.local/bin/rtk   # if needed

Step 2 — Identify the target agent group

ncl groups list

Note the group ID (e.g. ag-1776342942165-ptgddd). Repeat Steps 3–5 for each group.

Step 3 — Mount rtk into the container config

Mount the host rtk binary read-only into the container with the host-only add-mount verb. It is idempotent — re-running skips the entry if it is already present:

ncl groups config add-mount --id <group-id> \
  --host ~/.local/bin/rtk \
  --container /usr/local/bin/rtk \
  --ro

This verb is operator-only and runs host-side (via /setup, /customize, or /manage-mounts); it is rejected from inside a container.

The host root (~/.local/bin) must also be in the external mount allowlist at ~/.config/nanoclaw/mount-allowlist.json for the mount to take effect at spawn. Add it there if it isn't already.

Verify:

ncl groups config get --id <group-id>
# Look for the /usr/local/bin/rtk mount

Step 4 — Add the PreToolUse hook to settings.json

Each agent group has a settings.json at:

data/v2-sessions/<group-id>/.claude-shared/settings.json

This file is mounted at /home/node/.claude/settings.json inside the container and is read by Claude Code for hooks, env, and model config.

Add the PreToolUse entry with jq. This drops any existing rtk Bash hook first, then appends a fresh one, so it is safe to re-run without creating duplicates:

SETTINGS="data/v2-sessions/<group-id>/.claude-shared/settings.json"

jq '.hooks.PreToolUse = ((.hooks.PreToolUse // [])
      | map(select((.hooks // []) | any(.command == "rtk hook claude") | not)))
    + [{"matcher":"Bash","hooks":[{"type":"command","command":"rtk hook claude"}]}]' \
  "$SETTINGS" > /tmp/rtk-settings.json && mv /tmp/rtk-settings.json "$SETTINGS"

Step 5 — Restart the container

ncl groups restart --id <group-id>

Verify

Confirm the binary is executable inside the container so a missing or non-executable mount surfaces immediately rather than as a silent hook failure:

docker exec "$(docker ps --filter "name=<group-id>" --format '{{.Names}}' | head -1)" rtk --version

Then ask the agent to run git status or any other supported command. rtk intercepts it silently. Check savings with:

~/.local/bin/rtk gain

Troubleshooting

rtk: command not found inside the container

Mount wasn't applied or container wasn't restarted:

ncl groups config get --id <group-id>
# Look for the /usr/local/bin/rtk mount
ncl groups restart --id <group-id>

Hook not firing

Verify the hook is in settings.json:

jq '.hooks.PreToolUse' data/v2-sessions/<group-id>/.claude-shared/settings.json

If missing, re-run Step 4.

Binary won't execute — permission denied

chmod +x ~/.local/bin/rtk

Reviews

No reviews yet. Tell others what you thought.

Comments

No login needed. Share how it worked for you, ask a question, or note where it did not run.

No comments yet. Be the first to write one.

Comments are published right away. Do not include personal information such as email addresses or phone numbers. Up to 2 URLs.

0 / 1,000 characters

This form is protected by reCAPTCHA, and the Google Privacy Policy and Terms of Service apply.

More skills from this repository

add-anydoc

FreeSummary

Equip NanoClaw agents to convert attached office documents into Markdown locally using Firecrawl AnyDoc. Agents can read Word, PowerPoint, Excel, and text-based PDF files without uploading them to an external parsing service.

  • Reading and summarizing attached office documents
  • Converting documents without uploading them to an external service
  • Extracting text from text-based PDFs
nanocoai/nanoclaw31KUpdated Oct 21, 2026

Let a NanoClaw container agent call local models running in Atomic Chat. The skill adds an MCP server, a connection that exposes model listing and text generation as tools, while Claude continues to coordinate the work.

  • Delegate part of Claude's work to a local model
  • List models available in Atomic Chat
  • Generate an answer with a specified local model
nanocoai/nanoclaw31KUpdated Oct 21, 2026

add-clidash

FreeSummary

Add a read-only web dashboard for browsing NanoClaw agents, sessions, and other resources. It builds tables from command-line JSON output and includes message activity charts, recent logs, and a viewer for skills, profiles, and CLAUDE.md files.

  • Check agent and session status in a browser
  • Review message counts and daily activity
  • Read recent host logs
nanocoai/nanoclaw31KUpdated Oct 21, 2026

add-codex

FreeSummary

Add Codex as the agent that plans tasks and coordinates tools in NanoClaw. Choose it for individual groups alongside Claude, with conversation history and session resume using a ChatGPT subscription or OpenAI API key.

  • Adding Codex as a NanoClaw agent provider
  • Choosing Claude or Codex for each group
  • Setting up ChatGPT or API key authentication
nanocoai/nanoclaw31KUpdated Oct 21, 2026

add-cursor

FreeSummary

Install Cursor as an agent backend for NanoClaw groups using its local SDK. Set up authentication and container integration so groups can use Cursor for planning, MCP tools, streaming responses, and session continuation.

  • Install Cursor as a NanoClaw agent backend
  • Configure Cursor account sign-in or API key authentication
  • Switch a specific NanoClaw group to Cursor
nanocoai/nanoclaw31KUpdated Oct 21, 2026

add-dashboard

FreeSummary

Install a local NanoClaw dashboard to inspect agents, sessions, channels, messages, and users. It displays token usage, context usage, activity, and live logs using periodic data snapshots and a log forwarding module.

  • Checking agent and session status in one place
  • Reviewing token and context usage
  • Following live logs with level filters
nanocoai/nanoclaw31KUpdated Oct 21, 2026

See all skills by nanocoai

Report a problem with this skill